Zero Shot Transfer Image Classification On 4
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy |
|---|---|
| coca-contrastive-captioners-are-image-text | 96.5 |
| learning-transferable-visual-models-from | 88.9 |
| scaling-up-visual-and-vision-language | 92.2 |
| Model 4 | 96.8 |
| pali-a-jointly-scaled-multilingual-language | 81.97 |
| eva-clip-improved-training-techniques-for | 94.5 |
| pali-a-jointly-scaled-multilingual-language | 96.1 |
| combined-scaling-for-zero-shot-transfer | 95.7 |
| scaling-vision-transformers-to-22-billion | 96.0 |
| altclip-altering-the-language-encoder-in-clip | 87.2 |
| eva-clip-18b-scaling-clip-to-18-billion | 95.7 |
| lit-zero-shot-transfer-with-locked-image-text | 93.9 |